#attach packages
library(tidyverse)
library(janitor)
library(lubridate)
library(here)
library(sf)
library(tmap)
library(tsibble)
library(fable)
library(fabletools)
library(feasts)
library(forecast)
library(mapview)
library(paletteer)
us_renew <- read_csv(here("data", "renewables_cons_prod.csv")) %>%
clean_names()
renew_clean <- us_renew %>%
mutate(description = str_to_lower(description)) %>%
filter(str_detect(description, pattern = "consumption")) %>%
filter(!str_detect(description, pattern = "total")) # ! means do the opposite of what you ask
renew_date <- renew_clean %>%
mutate(yr_mo_day = lubridate::parse_date_time(yyyymm, "ym")) %>%
mutate(month_sep = yearmonth(yr_mo_day)) %>%
mutate(value = as.numeric(value)) %>%
drop_na(month_sep, value)
# make version where month and year are in separate columns:
renew_parsed <- renew_date %>%
mutate(month = month(yr_mo_day, label = TRUE)) %>%
mutate(year = year(yr_mo_day))
renew_gg <- ggplot(data = renew_date, aes(x = month_sep,
y = value,
group = description,
color = description)) +
geom_line() +
theme_bw()
renew_gg
Updating colors with paleteer palettes:
renew_gg +
scale_color_paletteer_d("nationalparkcolors::Badlands")
renew_ts <- as_tsibble(renew_parsed, key = description, index = month_sep)
look at time series data in a couple ways:
renew_ts %>%
autoplot(value)
renew_ts %>%
gg_subseries(value)
# renew_ts %>%
# gg_season(value)
ggplot(data = renew_parsed,
aes(x = month,
y = value,
group = year)) +
geom_line(aes(color = year)) +
facet_wrap(~description,
ncol = 1,
scales = "free",
strip.position = "right")
hydro_ts <- renew_ts %>%
filter(description == "hydroelectric power consumption")
hydro_ts %>%
autoplot(value)
hydro_ts %>%
gg_subseries(value)
#hydro_ts %>%
#gg_season(value)
ggplot(hydro_ts, aes(x = month,
y = value,
group = year)) +
geom_line(aes(color = year))
hydro_quarterly <- hydro_ts %>%
index_by(year_qu= ~(yearquarter(.))) %>%
summarize(avg_consumption = mean(value))
head(hydro_quarterly)
## # A tsibble: 6 x 2 [1Q]
## year_qu avg_consumption
## <qtr> <dbl>
## 1 1973 Q1 261.
## 2 1973 Q2 255.
## 3 1973 Q3 212.
## 4 1973 Q4 225.
## 5 1974 Q1 292.
## 6 1974 Q2 290.
dcmp <- hydro_ts %>%
model(STL(value ~ season(window = 5)))
components(dcmp) %>%
autoplot()
hist(components(dcmp)$remainder)
now we look at ACF
hydro_ts %>%
ACF(value) %>%
autoplot()
### DANGER FORECASTING!!!!!
hydro_model <- hydro_ts %>%
model(
ARIMA(value),
ETS(value)
) %>%
fabletools::forecast(h = "4 years")
hydro_model %>%
autoplot(filter(hydro_ts, year(month_sep) > 2010))
world <- read_sf(here("data", "TM_WORLD_BORDERS_SIMPL-0.3-1"),
layer = "TM_WORLD_BORDERS_SIMPL-0.3")
#mapview(world)